Depth Super-Resolution with Color Guidance: A Review

Depth super-resolution (SR) with color guidance is a classic vision problem to upsample low-resolution depth images. It has a wide range of applications in 3D reconstruction, automotive driver assistance and augmented reality. Due to the easy acquirement of the aligned high-resolution color images, there have been many depth SR approaches with color guidance in the past years. This chapter provides a comprehensive survey of the recent developments in this field. We divide these methods into three categories: regularization-based methods, filtering-based methods, and learning-based methods. Regularization-based methods make the ill-posed SR problem well constrained by utilizing regularization terms. Filtering-based methods upsample depth images via local filters with the instruction of guidance images. Learning-based methods can be further divided into traditional dictionary learning methods based …